Novel Slot Detection: A Benchmark for Discovering Unknown Slot Types in the Task-Oriented Dialogue System
Yanan Wu, Zhiyuan Zeng, Keqing He, Hong Xu, Yuanmeng Yan, Huixing Jiang, Weiran Xu
摘要
Existing slot filling models can only recognize pre-defined in-domain slot types from a limited slot set. In the practical application, a reliable dialogue system should know what it does not know. In this paper, we introduce a new task, Novel Slot Detection (NSD), in the task-oriented dialogue system. NSD aims to discover unknown or out-of-domain slot types to strengthen the capability of a dialogue system based on in-domain training data. Besides, we construct two public NSD datasets, propose several strong NSD baselines, and establish a benchmark for future work. Finally, we conduct exhaustive experiments and qualitative analysis to comprehend key challenges and provide new guidance for future directions 1 .
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式，引用它的顶会 Paper 也一样。你提问，回答直接引用原文。
引用它的顶会 Paper1
问问它们各自怎么用它相关 Paper
- Discovering Dialogue Slots with Weak SupervisionVojtech Hudecek, Ondrej Dusek, Zhou YuACL 2021
- Linguistically-Enriched and Context-AwareZero-shot Slot FillingA. B. Siddique, Fuad T. Jamour, Vagelis HristidisWWW 2021 · 被引用 29 次
- Automatic Intent-Slot Induction for Dialogue SystemsZengfeng Zeng, Dan Ma, Haiqin Yang, Zhen Gou 等WWW 2021 · 被引用 18 次
- Watch the Neighbors: A Unified K-Nearest Neighbor Contrastive Learning Framework for OOD Intent DiscoveryYutao Mou, Keqing He, Pei Wang, Yanan Wu 等EMNLP 2022 · 被引用 9 次
- Likelihood Ratios and Generative Classifiers for Unsupervised Out-of-Domain Detection in Task Oriented DialogVarun Gangal, Abhinav Arora, Arash Einolghozati, Sonal GuptaAAAI 2020 · 被引用 59 次
